Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Other

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	direction
    -0.07
    Crear
    -0.07
    elerinde
    -0.07
    illin
    -0.07
     کش
    -0.07
     sortable
    -0.07
    责任
    -0.07
    ihad
    -0.06
     ethn
    -0.06
    _bad
    -0.06
    POSITIVE LOGITS
     bewild
    0.08
     vitae
    0.06
    avez
    0.06
     limitless
    0.06
    υγ
    0.06
     appendix
    0.06
    chef
    0.06
    大学
    0.06
     olduğunu
    0.06
    <>
    0.06
    Act Density 0.001%

    No Known Activations